Continuing the discussion of the last two episodes, there is one more aspect of deep learning that I would love to consider and therefore left as a full episode, that is parallelising and distributing deep learning on relatively large clusters.
As a matter of fact, computing architectures are changing in a way that is encouraging parallelism more than ever before. And deep learning is no exception and despite the greatest improvements with commodity GPUs - graphical processing units, when it comes to speed, there is still room for improvement.
Together with the last two episodes, this one completes the picture of deep learning at scale. Indeed, as I mentioned in the previous episode, How to master optimisation in deep learning, the function optimizer is the horsepower of deep learning and neural networks in general. A slow and inaccurate optimisation method leads to networks that slowly converge to unreliable results.
In another episode titled “Additional strategies for optimizing deeplearning” I explained some ways to improve function minimisation and model tuning in order to get better parameters in less time. So feel free to listen to these episodes again, share them with your friends, even re-broadcast or download for your commute.
While the methods that I have explained so far represent a good starting point for prototyping a network, when you need to switch to production environments or take advantage of the most recent and advanced hardware capabilities of your GPU, well... in all those cases, you would like to do something more.
Episode 20: How to master optimisation in deep learning
Episode 19: How to completely change your data analytics strategy with deep learning
Episode 18: Machines that learn like humans
Episode 17: Protecting privacy and confidentiality in data and communications
Episode 16: 2017 Predictions in Data Science
Episode 15: Statistical analysis of phenomena that smell like chaos
Episode 14: The minimum required by a data scientist
Episode 13: Data Science and Fraud Detection at iZettle
Episode 12: EU Regulations and the rise of Data Hijackers
Episode 11: Representative Subsets For Big Data Learning
Episode 10: History and applications of Deep Learning
Episode 9: Markov Chain Montecarlo with full conditionals
Episode 8: Frequentists and Bayesians
Episode 7: 30 min with data scientist Sebastian Raschka
Episode 6: How to be data scientist
Episode 5: Development and Testing Practices in Data Science
Episode 1: Predictions in Data Science for 2016
Episode 4: BigData on your desk
Episode 2: Networks and Graph Databases
Episode 3: Data Science and Bio-Inspired Algorithms
Create your
podcast in
minutes
It is Free
Insight Story: Tech Trends Unpacked
Zero-Shot
Fast Forward by Tomorrow Unlocked: Tech past, tech future
The Unbelivable Truth - Series 1 - 26 including specials and pilot
Lex Fridman Podcast